Analysis of complexity and modulation spectra parameterizations to characterize voice roughness

Moro Velázquez, Laureano; Gómez García, Jorge Andrés y Godino Llorente, Juan Ignacio (2014). Analysis of complexity and modulation spectra parameterizations to characterize voice roughness. En: "IberSpeech 2014", 19/11/2014 - 21/11/2014, Las Palmas de Gran Canaria, Spain. pp. 1-10.

Descripción

Título: Analysis of complexity and modulation spectra parameterizations to characterize voice roughness
Autor/es:
  • Moro Velázquez, Laureano
  • Gómez García, Jorge Andrés
  • Godino Llorente, Juan Ignacio
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: IberSpeech 2014
Fechas del Evento: 19/11/2014 - 21/11/2014
Lugar del Evento: Las Palmas de Gran Canaria, Spain
Título del Libro: IberSPEECH 2014
Fecha: 2014
Materias:
Palabras Clave Informales: GRBAS, Complexity, Modulation Spectra, Kappa Index, GMM, voice pathology, Roughness
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Otro
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (1MB) | Vista Previa

Resumen

Disordered voices are frequently assessed by speech pathologists using acoustic perceptual evaluations. This might lead to problems due to the subjective nature of the process and due to the in uence of external factors which compromise the quality of the assessment. In order to increase the reliability of the evaluations the design of new indicator parameters obtained from voice signal processing is desirable. With that in mind, this paper presents an automatic evaluation system which emulates perceptual assessments of the roughness level in human voice. Two parameterization methods are used: complexity, which has already been used successfully in previous works, and modulation spectra. For the latter, a new group of parameters has been proposed as Low Modulation Ratio (LMR), Contrast (MSW) and Homogeneity (MSH). The tested methodology also employs PCA and LDA to reduce the dimensionality of the feature space, and GMM classiffers for evaluating the ability of the proposed features on distinguishing the different roughness levels. An effciency of 82% and a Cohen's Kappa Index of 0:73 is obtained using the modulation spectra parameters, while the complexity parameters performed 73% and 0:58 respectively. The obtained results indicate the usefulness of the proposed modulation spectra features for the automatic evaluation of voice roughness which can derive in new parameters to be useful for clinicians.

Proyectos asociados

TipoCódigoAcrónimoResponsableTítulo
Gobierno de EspañaTEC2012-38630-C04-01Sin especificarUniversidad Politécnica de MadridEvaluación multimodal de trastornos neurológicos mediante la caracterización de la voz, dinámica de los pliegues vocales y secuencias sacadicas
Comunidad de MadridSin especificarSin especificarSin especificarSin especificar

Más información

ID de Registro: 44611
Identificador DC: http://oa.upm.es/44611/
Identificador OAI: oai:oa.upm.es:44611
Depositado por: Memoria Investigacion
Depositado el: 07 Mar 2017 16:09
Ultima Modificación: 07 Mar 2017 16:09
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM